Computer Rating System Prediction Results for College Football (NCAA IA)

2014 Season Totals

Through
Rank System Pct. Correct Against Spread Absolute Error Bias Mean Square Error games suw sul atsw atsl
1Logistic Regression0.775510.5227315.0008-3.8163349.9744938112321
2Linear Regression0.775510.4090913.1845-0.9735269.3354938111826
3Line (updated)0.763640.5103411.89771.6500232.436440336104148142
4Computer Adjusted Line0.761360.4909111.96701.5966234.143440335105162168
5Thompson CAL0.758540.4765312.13121.6014237.926439333106203223
6Pigskin Index0.756820.4717412.62951.1253257.810440333107192215
7Thompson ATS0.756260.4835712.12481.2314238.798439332107206220
8Line (Midweek)0.7545511.96481.5739235.492440332108
9Pi-Rate Ratings0.752270.5316212.51401.7773256.412440331109227200
10Dunkel Index0.750000.5199113.03471.7366292.453440330110222205
11Dokter Entropy0.750000.4859212.35261.6272246.125440330110207219
12DP Dwiggins0.749350.4490413.67621.4726293.43038328796163200
13Billingsley+0.747730.4894613.00620.7110276.673440329111209218
14Sagarin Ratings0.747730.4519912.88571.8071265.907440329111193234
15Thompson Average0.747150.4704512.32361.5235245.878439328111199224
16PI-Rate Bias0.745450.5379112.49211.6420252.583440328112227195
17System Median0.745450.4773312.53351.3114252.214440328112200219
18Sagarin Points0.745450.4613612.77851.8795267.970440328112197230
19Atomic Football0.743180.4806812.52901.6476252.827440327113199215
20CPA Rankings0.743180.4871213.17221.0717268.736440327113208219
21Billingsley0.743180.4918013.57240.2235302.319440327113210217
22Line (opening)0.740910.5041612.10801.4011237.322440326114182179
23Nutshell Girl0.738760.5160314.8439-2.6726381.94635626393177166
24DirectorOfInformation0.738640.4894612.85981.0664269.602440325115209218
25Massey Consensus0.738640.4683813.16111.6121275.636440325115200227
26Pi-Ratings Mean0.736360.5471712.37131.2282245.838440324116232192
27System Average0.736360.4671412.57371.2764254.342440324116199227
28Catherwood Ratings0.735760.4572113.65831.7768301.984439323116187222
29NutShell Combo0.734620.4596812.86461.1497276.36726019169114134
30Sagarin Golden Mean0.734090.4730713.29591.6892279.620440323117202225
31Randal Horobik0.734090.4665013.59321.5569287.011440323117188215
32NutShell Sports0.732880.4855813.93770.2370321.553438321117202214
33Lee Burdorf0.732880.4940913.44951.1422286.739438321117209214
34Ashby AccuRatings0.731820.4655212.64771.0797255.269440322118189217
35Moore Power Ratings0.729980.4504713.57501.6851299.367437319118191233
36Stat Fox0.729550.4600513.26132.1572288.541440321119190223
37Massey Ratings0.729550.4498813.03640.7545272.242440321119184225
38Brent Craig0.728930.4517613.31911.8204277.460439320119192233
39Dave Congrove0.727270.4590213.86520.5163315.658440320120196231
40Keeper0.727270.4683813.75102.5209297.974440320120200227
41ComPughter Ratings0.727270.4871213.07761.1413272.807440320120208219
42Cleanup Hitter0.725710.5208315.1490-1.6334395.33835025496175161
43ThePowerRank.com0.725120.4878012.61570.7175261.111422306116200210
44Regression Based Analys0.725000.4352114.07952.5386313.051440319121178231
45Edward Kambour0.724940.4711513.27961.4991282.688429311118196220
46Brent Craig 20.724250.4879715.6717-1.2538401.55430121883142149
47Payne Power Ratings0.722730.4754113.40061.0474284.223440318122203224
48Sagarin Points Elo0.720450.4730713.55121.6464293.049440317123202225
49MDS Model0.719820.5117413.69070.4124307.857439316123218208
50ARGH Power Ratings0.718180.4509813.49381.2926284.729440316124184224
51Born Power Index0.715910.4496514.18031.5233313.854440315125192235
52Laz Index0.715910.4964913.08780.5376273.818440315125212215
53Daniel Curry Index0.715910.4694814.61661.3139342.895440315125200226
54Beck Elo0.715400.4423613.67961.2967291.207383274109165208
55Least Squares w/ HFA0.714290.4318215.8847-1.3182410.0954935141925
56Tempo Free Gridiron0.713640.5154413.3886-0.6886300.069440314126217204
57Stephen Kerns0.711540.4461214.0805-0.0833309.788416296120178221
58FEI Projections0.708430.5060513.30980.7039285.600439311128209204
59Super List0.706820.5234714.32511.4531329.068440311129223203
60CPA Retro0.706820.4754114.14740.9867310.818440311129203224
61PerformanZ Ratings0.704550.4543314.27410.9073320.129440310130194233
62Nutshell Eye0.703850.4732513.06251.2991278.71926018377115128
63Sportrends0.702350.4888914.5405-1.0313356.107383269114176184
64Laffaye XWP0.700000.4600916.72957.1809433.707440308132196230
65Marsee0.700000.4457814.22953.0568319.063440308132185230
66Howell0.697040.4864913.76090.9067301.727439306133198209
67Covers.com0.695450.5200913.6425-0.2737308.375440306134220203
68Donchess Inference0.694060.4658813.58310.3333293.967438304134198227
69Laffaye RWP0.688640.5292714.0415-1.5332320.149440303137226201
70Bihl System0.675500.4305613.56271.9187283.588151102496282
71PointShare0.650000.5020213.83380.9685301.98526016991124123

* This system does not make predictions.  I make predictions for this
  system by translating it to a new scale that allows for making predictions.



Retrodictive records are found by taking the ratings from the current week
and applying them to the entire season to date.

The ideal system would be one that has the highest correct game decisions,
has the smallest mean error(deviation from the actual game result), and has
a bias of zero.

Mean Error = average[abs(prediction-actual)]

      Bias = agerage(prediction - actual)

      Std. = Standard Deviation of individual game biases